© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 124015
    Prev
    Next
    INDEX
    Explanations

    void methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Erinner
    -1.79
     kendini
    -1.76
     neuen
    -1.73
    ↵↵
    -1.66
     besonderen
    -1.65
     would
    -1.63
     t
    -1.63
     wahren
    -1.59
     rendition
    -1.59
     This
    -1.58
    POSITIVE LOGITS
    鼉
    2.19
    狴
    1.64
     baumwolle
    1.63
     zitate
    1.59
    還在
    1.58
     hata
    1.58
    1.58
    '
    1.56
     tirs
    1.55
     rangs
    1.53
    Activations Density 0.005%

    No Known Activations